Automatically Designing CNN Architectures Using the Genetic Algorithm for Image Classification

By Yanan Sun, Bing Xue, Mengjie Zhang, Gary G. Yen, Jiancheng Lv. 2018

729 citations recorded by the source corpus.

Convolutional neural networks (CNNs) have gained remarkable success on many image classification tasks in recent years. However, the performance of CNNs highly relies upon their architectures. For the most state-of-the-art CNNs, their architectures are often manually designed with expertise in both CNNs and the investigated problems. Therefore, it is difficult for users, who have no extended expertise in CNNs, to design optimal CNN architectures for their own image classification problems of interest. In this article, we propose an automatic CNN architecture design method by using genetic algorithms, to effectively address the image classification tasks. The most merit of the proposed algorithm remains in its “automatic” characteristic that users do not need domain knowledge of CNNs when using the proposed algorithm, while they can still obtain a promising CNN architecture for the given images. The proposed algorithm is validated on widely used benchmark image classification datasets, compared to the state-of-the-art peer competitors covering eight manually designed CNNs, seven automatic + manually tuning, and five automatic CNN architecture design algorithms. The experimental results indicate the proposed algorithm outperforms the existing automatic CNN architecture design algorithms in terms of classification accuracy, parameter numbers, and consumed computational resources. The proposed algorithm also shows the very comparable classification accuracy to the best one from manually designed and automatic + manually tuning CNNs, while consuming fewer computational resources.

Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

In Computer Vision and Pattern Recognition

Citations in the corpus

Surrogate-Assisted Evolutionary Deep Learning Using an End-to-End Random Forest-Based Performance Predictor (2020, methodology): “As a result, the potential promising architecture may not be found through EDLs within a limited computational budget due to the time-consuming ﬁtness evaluation.”
A Survey on Evolutionary Neural Architecture Search (2020, methodology): “However, the supplemental materials in [24] demonstrated the effectiveness of the crossover operator in this method.”
Activation Functions: Comparison of trends in Practice and Research for Deep Learning (2018, result): “Automatically designing the CNN architecture represents an emerging network design trend and researchers have suggested that it produces comparable results to the manually designed architectures [57].”
Genetic algorithms: theory, genetic operators, solutions, and applications (2023, neutral): “GAs have been used to solve optimization problems in several applications such as image processing [54–57], scheduling [54, 58, 59], clustering [60–62], software engineering [63–66], natural language processing [67, 68], and recommender system (RS) [52, 69, 70].”
Unmanned Aircraft System (UAS) Technology and Applications in Agriculture (2019, background): “, where the lines and shapes from lower levels begin to form objects and more complex structures) to be able to develop new classification filters for any unique dataset [35,121].”